← Back to all models

llama2 embedding 1b 8k

Embedding model by mesolitica · 0.95B parameters

Chip
Unified Memory
Bandwidth 307 GB/s
Available for Models ~21 GB

Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro

Runs Excellently

llama2 embedding 1b 8k fits comfortably in your 24 GB Mac using Q8_0 quantization, using 6% of your RAM.

~169 tok/s

Q8_0 · 1.6 GB · Estimated

Quantization Options

QuantizationMemorySpeedFits?
Q8_0 Recommended 1.6 GB~169 tok/s
Q6_K 1.3 GB~222 tok/s
Q5_K_M 1.2 GB~261 tok/s
Q4_K_M 1.1 GB~306 tok/s
Q3_K_M 1.0 GB~370 tok/s
Q2_K 0.9 GB~480 tok/s

Specifications

Parameters947M
Architecturellama
Context Length33K
CategoryEmbedding
Formatgguf
Minimum RAM1 GB
HuggingFace Downloads272,119

Which Mac Can Run llama2 embedding 1b 8k?

Minimum Mac

MacBook Air — M2 8GB

Q8_0 · ~55 tok/s · 19% RAM

MacQuanttok/sRAM %
Mac Studio · M3 Ultra 96GB Q8_0 ~452 2%
Mac Studio · M3 Ultra 256GB Q8_0 ~452 1%
Mac Studio · M3 Ultra 512GB Q8_0 ~452 0%
Mac Studio · M1 Ultra 64GB Q8_0 ~441 2%
Mac Studio · M1 Ultra 128GB Q8_0 ~441 1%
Mac Studio · M2 Ultra 64GB Q8_0 ~441 2%
Mac Studio · M2 Ultra 128GB Q8_0 ~441 1%
Mac Studio · M2 Ultra 192GB Q8_0 ~441 1%
MacBook Pro 14" · M5 Max 36GB Q8_0 ~339 4%
MacBook Pro 14" · M5 Max 48GB Q8_0 ~339 3%
MacBook Pro 14" · M5 Max 64GB Q8_0 ~339 2%
MacBook Pro 14" · M5 Max 128GB Q8_0 ~339 1%
MacBook Pro 16" · M5 Max 36GB Q8_0 ~339 4%
MacBook Pro 16" · M5 Max 48GB Q8_0 ~339 3%
MacBook Pro 16" · M5 Max 64GB Q8_0 ~339 2%
MacBook Pro 16" · M5 Max 128GB Q8_0 ~339 1%
MacBook Pro 14" · M4 Max 36GB Q8_0 ~301 4%
MacBook Pro 14" · M4 Max 48GB Q8_0 ~301 3%
MacBook Pro 14" · M4 Max 64GB Q8_0 ~301 2%
MacBook Pro 14" · M4 Max 128GB Q8_0 ~301 1%
MacBook Pro 16" · M4 Max 36GB Q8_0 ~301 4%
MacBook Pro 16" · M4 Max 48GB Q8_0 ~301 3%
MacBook Pro 16" · M4 Max 64GB Q8_0 ~301 2%
MacBook Pro 16" · M4 Max 128GB Q8_0 ~301 1%
Mac Studio · M4 Max 36GB Q8_0 ~301 4%
Mac Studio · M4 Max 48GB Q8_0 ~301 3%
Mac Studio · M4 Max 64GB Q8_0 ~301 2%
Mac Studio · M4 Max 128GB Q8_0 ~301 1%
MacBook Pro 14" · M1 Max 32GB Q8_0 ~221 5%
MacBook Pro 14" · M1 Max 64GB Q8_0 ~221 2%
MacBook Pro 14" · M2 Max 32GB Q8_0 ~221 5%
MacBook Pro 14" · M2 Max 64GB Q8_0 ~221 2%
MacBook Pro 14" · M2 Max 96GB Q8_0 ~221 2%
MacBook Pro 14" · M3 Max 36GB Q8_0 ~221 4%
MacBook Pro 14" · M3 Max 48GB Q8_0 ~221 3%
MacBook Pro 14" · M3 Max 64GB Q8_0 ~221 2%
MacBook Pro 14" · M3 Max 96GB Q8_0 ~221 2%
MacBook Pro 14" · M3 Max 128GB Q8_0 ~221 1%
MacBook Pro 16" · M1 Max 32GB Q8_0 ~221 5%
MacBook Pro 16" · M1 Max 64GB Q8_0 ~221 2%
MacBook Pro 16" · M2 Max 32GB Q8_0 ~221 5%
MacBook Pro 16" · M2 Max 64GB Q8_0 ~221 2%
MacBook Pro 16" · M2 Max 96GB Q8_0 ~221 2%
MacBook Pro 16" · M3 Max 36GB Q8_0 ~221 4%
MacBook Pro 16" · M3 Max 48GB Q8_0 ~221 3%
MacBook Pro 16" · M3 Max 64GB Q8_0 ~221 2%
MacBook Pro 16" · M3 Max 96GB Q8_0 ~221 2%
MacBook Pro 16" · M3 Max 128GB Q8_0 ~221 1%
Mac Studio · M1 Max 32GB Q8_0 ~221 5%
Mac Studio · M1 Max 64GB Q8_0 ~221 2%
Mac Studio · M2 Max 32GB Q8_0 ~221 5%
Mac Studio · M2 Max 64GB Q8_0 ~221 2%
Mac Studio · M2 Max 96GB Q8_0 ~221 2%
MacBook Pro 14" · M5 Pro 24GB Q8_0 ~169 6%
MacBook Pro 14" · M5 Pro 48GB Q8_0 ~169 3%
MacBook Pro 14" · M5 Pro 64GB Q8_0 ~169 2%
MacBook Pro 16" · M5 Pro 24GB Q8_0 ~169 6%
MacBook Pro 16" · M5 Pro 48GB Q8_0 ~169 3%
MacBook Pro 16" · M5 Pro 64GB Q8_0 ~169 2%
MacBook Pro 14" · M4 Pro 24GB Q8_0 ~151 6%
MacBook Pro 14" · M4 Pro 48GB Q8_0 ~151 3%
MacBook Pro 16" · M4 Pro 24GB Q8_0 ~151 6%
MacBook Pro 16" · M4 Pro 48GB Q8_0 ~151 3%
Mac mini · M4 Pro 24GB Q8_0 ~151 6%
Mac mini · M4 Pro 48GB Q8_0 ~151 3%
Mac mini · M4 Pro 64GB Q8_0 ~151 2%
MacBook Pro 14" · M1 Pro 16GB Q8_0 ~110 10%
MacBook Pro 14" · M1 Pro 32GB Q8_0 ~110 5%
MacBook Pro 14" · M2 Pro 16GB Q8_0 ~110 10%
MacBook Pro 14" · M2 Pro 32GB Q8_0 ~110 5%
MacBook Pro 16" · M1 Pro 16GB Q8_0 ~110 10%
MacBook Pro 16" · M1 Pro 32GB Q8_0 ~110 5%
MacBook Pro 16" · M2 Pro 16GB Q8_0 ~110 10%
MacBook Pro 16" · M2 Pro 32GB Q8_0 ~110 5%
Mac mini · M2 Pro 16GB Q8_0 ~110 10%
Mac mini · M2 Pro 32GB Q8_0 ~110 5%
MacBook Air · M5 16GB Q8_0 ~84 10%
MacBook Air · M5 24GB Q8_0 ~84 6%
MacBook Air · M5 32GB Q8_0 ~84 5%
MacBook Pro 14" · M5 16GB Q8_0 ~84 10%
MacBook Pro 14" · M5 24GB Q8_0 ~84 6%
MacBook Pro 14" · M5 32GB Q8_0 ~84 5%
MacBook Pro 14" · M3 Pro 18GB Q8_0 ~83 9%
MacBook Pro 14" · M3 Pro 36GB Q8_0 ~83 4%
MacBook Pro 16" · M3 Pro 18GB Q8_0 ~83 9%
MacBook Pro 16" · M3 Pro 36GB Q8_0 ~83 4%
MacBook Air · M4 16GB Q8_0 ~66 10%
MacBook Air · M4 24GB Q8_0 ~66 6%
MacBook Air · M4 32GB Q8_0 ~66 5%
MacBook Pro 14" · M4 16GB Q8_0 ~66 10%
MacBook Pro 14" · M4 24GB Q8_0 ~66 6%
MacBook Pro 14" · M4 32GB Q8_0 ~66 5%
Mac mini · M4 16GB Q8_0 ~66 10%
Mac mini · M4 24GB Q8_0 ~66 6%
Mac mini · M4 32GB Q8_0 ~66 5%
iMac · M4 16GB Q8_0 ~66 10%
iMac · M4 24GB Q8_0 ~66 6%
iMac · M4 32GB Q8_0 ~66 5%
MacBook Air · M2 8GB Q8_0 ~55 19%
MacBook Air · M2 16GB Q8_0 ~55 10%
MacBook Air · M2 24GB Q8_0 ~55 6%
MacBook Air · M3 8GB Q8_0 ~55 19%
MacBook Air · M3 16GB Q8_0 ~55 10%
MacBook Air · M3 24GB Q8_0 ~55 6%
MacBook Pro 14" · M3 8GB Q8_0 ~55 19%
MacBook Pro 14" · M3 16GB Q8_0 ~55 10%
MacBook Pro 14" · M3 24GB Q8_0 ~55 6%
Mac mini · M2 8GB Q8_0 ~55 19%
Mac mini · M2 16GB Q8_0 ~55 10%
Mac mini · M2 24GB Q8_0 ~55 6%
iMac · M3 8GB Q8_0 ~55 19%
iMac · M3 16GB Q8_0 ~55 10%
iMac · M3 24GB Q8_0 ~55 6%
MacBook Air · M1 8GB Q8_0 ~38 19%
MacBook Air · M1 16GB Q8_0 ~38 10%
Mac mini · M1 8GB Q8_0 ~38 19%
Mac mini · M1 16GB Q8_0 ~38 10%
iMac · M1 8GB Q8_0 ~38 19%
iMac · M1 16GB Q8_0 ~38 10%

Run llama2 embedding 1b 8k locally on your Mac

ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.

Get ToolPiper — Free